Resolving lexical ambiguity computationally with spreading activation and Polaroid Words. Hirst, G. Small, S., Cottrell, G., & Tanenhaus, M., editors. Lexical ambiguity resolution, pages 73–107. Los Altos, CA: Morgan Kaufmann, 1988. 2003 epilogue to this paper:  PDF
abstract   bibtex   

Any computer system for understanding natural language input (even in relatively weak senses of the word understanding) needs to be able to resolve lexical ambiguities. In this paper, I describe the lexical ambiguity resolution component of one such system.

The basic strategy used for disambiguation is ``do it the way people do.'' While cognitive modeling is not the primary goal of this work, it is often a good strategy in artificial intelligence to consider cognitive modeling anyway; finding out how people do something and trying to copy them is a good way to get a program to do the same thing. In developing the system below, I was strongly influenced by psycholinguistic research on lexical access and negative priming—in particular by the results of Swinney; Seidenberg, Tanenhaus, Leiman, and Bienkowski; and Reder. I will discuss the degree to which the system is a model of ambiguity resolution in people.

@InBook{	  hirst30,
  author	= {Graeme Hirst},
  chapter	= {Resolving lexical ambiguity computationally with spreading
		  activation and Polaroid Words},
  title		= {Lexical ambiguity resolution},
  editor	= {Steven Small and Garrison Cottrell and Michael Tanenhaus},
  publisher	= {Los Altos, CA: Morgan Kaufmann},
  year		= {1988},
  pages		= {73--107},
  note		= {2003 epilogue to this paper:&nbsp; <a
		  href=http://ftp.cs.toronto.edu/pub/gh/Hirst-88-Epilogue-2003.pdf>PDF</a>}
		  ,
  abstract	= {<p> Any computer system for understanding natural language
		  input (even in relatively weak senses of the word
		  <i>understanding</i>) needs to be able to resolve lexical
		  ambiguities. In this paper, I describe the lexical
		  ambiguity resolution component of one such system. </p><p>
		  The basic strategy used for disambiguation is ``do it the
		  way people do.'' While cognitive modeling is not the
		  primary goal of this work, it is often a good strategy in
		  artificial intelligence to consider cognitive modeling
		  anyway; finding out how people do something and trying to
		  copy them is a good way to get a program to do the same
		  thing. In developing the system below, I was strongly
		  influenced by psycholinguistic research on lexical access
		  and negative priming---in particular by the results of
		  Swinney; Seidenberg, Tanenhaus, Leiman, and Bienkowski; and
		  Reder. I will discuss the degree to which the system is a
		  model of ambiguity resolution in people.</p>},
  download	= {http://ftp.cs.toronto.edu/pub/gh/Hirst-88.pdf}
}

Downloads: 0